Skip to main content

Khmer OCR — Image to Text & PDF

ស្រង់អត្តបទភាសាខ្មែរពីរូបភាពនិងឯកសារក្រុម

Free · No registration for images · AI-powered

Drop your file here

PNG, JPG, PDF

Khmer script recognition

Full support for Khmer consonants, vowels, and subscript forms.

Subscript consonants

Correctly handles below-base consonants (coeng) used in Khmer.

Complex vowels

Recognizes Khmer vowel diacritics that surround consonants on multiple sides.

Mixed Khmer & English

Bilingual documents with Khmer and Latin scripts handled in one pass.

Searchable PDF output

Creates PDFs with invisible text layer for full-text search.

Translate after extraction

Extract Khmer text then translate to English or any language.

Why Khmer OCR Is Challenging

  • Recognizing subscript consonants (coeng) that appear below base characters and modify pronunciation
  • Handling complex vowel diacritics that can appear above, below, before, or after consonants
  • Distinguishing visually similar Khmer characters like ក/គ, ច/ឆ, ត/ថ in small fonts
  • Processing stacked combinations where subscript consonants and vowel marks pile up
  • Correctly segmenting Khmer text which has no spaces between words

How to Extract Khmer Text from a PDF & Images

  1. Go to fastocr.org
  2. Upload your Khmer image or PDF. Language is detected automatically.
  3. Wait for processing — images take seconds, PDFs show a progress bar.
  4. Download results: searchable PDF, raw text file, or copy text directly.

Tips for Better Khmer OCR Accuracy

  1. Scan at 300 DPI minimum to preserve the subscript consonant details below base characters
  2. Use clean, high-contrast scans to prevent subscript marks from merging with base characters
  3. Verify that subscript consonants (coeng) are not lost or merged in the output
  4. For documents with complex vowel stacks, increase image brightness to improve mark separation

Common Use Cases for Khmer OCR

  • Digitizing Cambodian legal documents, contracts, and government records
  • Extracting text from Khmer academic papers and university publications
  • Converting scanned Buddhist texts and historical Cambodian manuscripts
  • Processing Khmer business invoices and commercial correspondence
  • Archiving Angkor-era inscriptions and historical Khmer stone carvings

Frequently Asked Questions

How accurate is Khmer OCR?

FastOCR achieves 93% accuracy on printed Khmer text. Subscript consonants and complex vowel stacking present challenges that may reduce accuracy on degraded scans.

Can Khmer OCR handle subscript consonants (coeng)?

Yes. FastOCR correctly identifies subscript consonants marked with the coeng sign. High-resolution scans (300+ DPI) ensure the small subscript forms are accurately recognized.

Is Khmer OCR free?

Yes. Image OCR is free with no registration. PDF processing requires a free account — see fastocr.org/pricing for plan details.

What file formats are supported for Khmer OCR?

FastOCR supports JPG, PNG, GIF, WebP, BMP images and PDF documents. Max 20MB for images, 1GB for PDFs.

Upload Khmer text →

Free for images. No registration required.